Training in progress, step 160, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea24a06d4297cb7bc9a35aaa42d564a5666190bf2fe714ed3d34247746608f5f
+oid sha256:706e09d4bf9933ddb5fabda6b8c5f9d74d24c10bf155ccc13184acd93e4d1ab4
 size 1579384

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e1cf8d4457b46c5d8fa05b2f35ee8ddf4c1df71c1017622a65d418ecc7b2a0e9
+oid sha256:5766353332fb305f49bebe1e2e0337a74ff7d9408989efba803ce4256f7fe826
 size 857274

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:056a3c074142756e34db3a1d83ef56a2230b3ca87d2eb93ba1fc46523c99e84f
+oid sha256:aa5a5d1a33e5ca36cbafb461e09204198d05c7ff6494a37033d5d14176625399
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b8fa6a7a6709edeb55cdf23229934c07be2d8aae0e4056fbdb6ff2482d0eb3d3
+oid sha256:ac2f052986474c47aa92ee09f81c986cf5cd3c01bde827e5d887e85b2bbda4c2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.2816241383552551,
   "best_model_checkpoint": "miner_id_24/checkpoint-130",
-  "epoch": 0.074064930255524,
+  "epoch": 0.07900259227255894,
   "eval_steps": 10,
-  "global_step": 150,
+  "global_step": 160,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1185,6 +1185,84 @@
       "eval_samples_per_second": 28.018,
       "eval_steps_per_second": 28.018,
       "step": 150
+    },
+    {
+      "epoch": 0.0745586964572275,
+      "grad_norm": 216.89869689941406,
+      "learning_rate": 0.00016184643766056317,
+      "loss": 1.9158,
+      "step": 151
+    },
+    {
+      "epoch": 0.075052462658931,
+      "grad_norm": 2457.674072265625,
+      "learning_rate": 0.00016134135287043669,
+      "loss": 2.4605,
+      "step": 152
+    },
+    {
+      "epoch": 0.07554622886063449,
+      "grad_norm": 1994.4697265625,
+      "learning_rate": 0.00016083374657755134,
+      "loss": 4.3665,
+      "step": 153
+    },
+    {
+      "epoch": 0.07603999506233798,
+      "grad_norm": 812.1641845703125,
+      "learning_rate": 0.00016032363964761363,
+      "loss": 0.5252,
+      "step": 154
+    },
+    {
+      "epoch": 0.07653376126404147,
+      "grad_norm": 978.52294921875,
+      "learning_rate": 0.00015981105304912162,
+      "loss": 2.1287,
+      "step": 155
+    },
+    {
+      "epoch": 0.07702752746574497,
+      "grad_norm": 10419.509765625,
+      "learning_rate": 0.00015929600785250257,
+      "loss": 0.9229,
+      "step": 156
+    },
+    {
+      "epoch": 0.07752129366744846,
+      "grad_norm": 1868.2894287109375,
+      "learning_rate": 0.00015877852522924732,
+      "loss": 2.6291,
+      "step": 157
+    },
+    {
+      "epoch": 0.07801505986915196,
+      "grad_norm": 595.7179565429688,
+      "learning_rate": 0.0001582586264510396,
+      "loss": 0.3959,
+      "step": 158
+    },
+    {
+      "epoch": 0.07850882607085545,
+      "grad_norm": 5246.302734375,
+      "learning_rate": 0.00015773633288888197,
+      "loss": 0.9382,
+      "step": 159
+    },
+    {
+      "epoch": 0.07900259227255894,
+      "grad_norm": 2367.507080078125,
+      "learning_rate": 0.00015721166601221698,
+      "loss": 0.6265,
+      "step": 160
+    },
+    {
+      "epoch": 0.07900259227255894,
+      "eval_loss": 0.3629942238330841,
+      "eval_runtime": 15.208,
+      "eval_samples_per_second": 28.077,
+      "eval_steps_per_second": 28.077,
+      "step": 160
     }
   ],
   "logging_steps": 1,
@@ -1199,7 +1277,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 2
+        "early_stopping_patience_counter": 3
       }
     },
     "TrainerControl": {
@@ -1208,12 +1286,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 118289439129600.0,
+  "total_flos": 126175401738240.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null